Skip to main content
Glama
Sign In

congressgov-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Congress.gov Daily Record

congressgov_daily_record
Read-onlyIdempotent

Browse the daily Congressional Record — floor speeches, debates, and legislative text published each day Congress is in session. Navigation is hierarchical: volumes (via 'list') → issues (via 'issues') → articles (via 'articles'). Use 'list' to find recent volumes, 'issues' to see what's in a volume, and 'articles' to access individual speeches and debate sections. 'articles' lists each article and its format URLs; 'content' then reads one article's actual text, a bounded character window at a time.

Input Schema

NameRequiredDescriptionDefault
limitNoResults per page (1-250).
formatNoDocument format for 'content'. 'text' is GPO's Formatted Text — plain, pre-formatted print output, published for every document checked. 'xml' prefers United States Legislative Markup and falls back to Formatted XML; it exists on some bill text versions and on no committee report or Congressional Record article. PDF is not retrieved — read one at the format URLs 'text'/'articles' return.text
offsetNoPagination offset.
operationYesWhich data to retrieve.
issueNumberNoIssue number within a volume. Required for 'articles' and 'content'. List rows carry this as a string (e.g. "109") — both forms are accepted.
articleIndexNoWhich article 'content' reads, 0-based against the issue's whole article sequence — the same absolute position 'articles' pages through with offset. Ignored by other operations.
volumeNumberNoVolume number. Required for 'issues', 'articles', and 'content'. Accepts a number or the digit-string form list rows carry.
characterLimitNoMaximum characters to return for 'content' (1-100000). Legislative documents run past a million characters, so a full bill takes several windows.
characterOffsetNoFirst character to return for 'content', 0-based. Offsets are exact and are never snapped to a section or paragraph break, so feeding the response's nextOffset back walks the whole document with every character returned exactly once.

Output Schema

NameRequiredDescriptionDefault
dataNoResult rows. Per-tool item shape is rendered in the markdown body.
errorNoPresent when the call failed. Absent on success.
noticeNoGuidance when results are empty, a page is past the end, or a caveat applies.
contentNoDynamic upstream JSON record.
paginationNoPagination metadata: total count and next offset.
totalCountNoTotal results across all pages.
effectiveQueryNoThe browse scope and applied filters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: A process-local attempt budget or the shared upstream credential/IP quota was reached; upstream hourly limits vary and DEMO_KEY also has a daily quota. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `upstream_timeout`: The Congress.gov request deadline expired or the upstream returned an HTTP timeout response. `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of every text the call would window — the document on 'content', or every returned row's summary text on 'summaries' — so the window would be empty. `incompatible_identity`: A list operation carries an entity identifier that only a detail operation uses. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: A process-local attempt budget or the shared upstream credential/IP quota was reached; upstream hourly limits vary and DEMO_KEY also has a daily quota. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `api_key_rejected`: The api.data.gov gateway rejected the server's configured CONGRESS_API_KEY (missing, invalid, disabled, unauthorized, or unverified); the gateway code is in data.upstreamCode. No change to the call's arguments can fix it. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status) or could not be reached, or the Senate LIS feed failed (5xx, a timeout, or a senate.gov HTTP 403 refusal, which carries retryable: false). `upstream_timeout`: A Congress.gov request or a congress.gov document fetch timed out or returned an HTTP timeout response, or the call's upstream requests could not finish inside its 50-second budget. `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of every text the call would window — the document on 'content', or every returned row's summary text on 'summaries' — so the window would be empty. `incompatible_identity`: A list operation carries an entity identifier that only a detail operation uses. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
-  "not_found",
-  "rate_limited",
-  "invalid_request",
-  "upstream_error",
-  "upstream_timeout",
-  "document_unavailable",
-  "format_unavailable",
-  "document_fetch_failed",
-  "document_too_large",
-  "offset_past_end",
-  "incompatible_identity"
-]New value: +[
+  "not_found",
+  "rate_limited",
+  "invalid_request",
+  "api_key_rejected",
+  "upstream_error",
+  "upstream_timeout",
+  "document_unavailable",
+  "format_unavailable",
+  "document_fetch_failed",
+  "document_too_large",
+  "offset_past_end",
+  "incompatible_identity"
+]
  2. Changed2 schema fields changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: The Congress.gov API rate limit (5,000 requests/hour per key) was exceeded. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of every text the call would window — the document on 'content', or every returned row's summary text on 'summaries' — so the window would be empty. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: A process-local attempt budget or the shared upstream credential/IP quota was reached; upstream hourly limits vary and DEMO_KEY also has a daily quota. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `upstream_timeout`: The Congress.gov request deadline expired or the upstream returned an HTTP timeout response. `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of every text the call would window — the document on 'content', or every returned row's summary text on 'summaries' — so the window would be empty. `incompatible_identity`: A list operation carries an entity identifier that only a detail operation uses. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
-  "not_found",
-  "rate_limited",
-  "invalid_request",
-  "upstream_error",
-  "document_unavailable",
-  "format_unavailable",
-  "document_fetch_failed",
-  "document_too_large",
-  "offset_past_end"
-]New value: +[
+  "not_found",
+  "rate_limited",
+  "invalid_request",
+  "upstream_error",
+  "upstream_timeout",
+  "document_unavailable",
+  "format_unavailable",
+  "document_fetch_failed",
+  "document_too_large",
+  "offset_past_end",
+  "incompatible_identity"
+]
  3. Changed1 schema field changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: The Congress.gov API rate limit (5,000 requests/hour per key) was exceeded. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of the document, so the window would be empty. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: The Congress.gov API rate limit (5,000 requests/hour per key) was exceeded. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of every text the call would window — the document on 'content', or every returned row's summary text on 'summaries' — so the window would be empty. Other values are possible when a failure originates below the handler."
  4. Changed1 schema field changed
    • addedOutput schema / properties / content
      Added value: +{
+  "additionalProperties": {},
+  "description": "Dynamic upstream JSON record.",
+  "properties": {},
+  "type": "object"
+}
  5. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "effectiveQuery",
+      "totalCount"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • addedOutput schema / properties / error
      Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: The Congress.gov API rate limit (5,000 requests/hour per key) was exceeded. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `document_unavailable`: The 'content' selection resolves to no retrievable document — the text version or article index is past the end of the list, the record publishes no formats at all, or Congress.gov does not hold the file its own metadata names. `format_unavailable`: The document exists but publishes nothing in the requested 'format' — some text versions and committee reports ship PDF only, and no Congressional Record article publishes XML. `document_fetch_failed`: www.congress.gov did not return a readable document — a non-2xx status, a network failure, an empty body, or a content type that is not text or XML. `document_too_large`: The document is larger than the byte ceiling this server retrieves, so no character window can be served from it. `offset_past_end`: characterOffset is at or beyond the last character of the document, so the window would be empty. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "not_found",
+            "rate_limited",
+            "invalid_request",
+            "upstream_error",
+            "document_unavailable",
+            "format_unavailable",
+            "document_fetch_failed",
+            "document_too_large",
+            "offset_past_end"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}
    • removedOutput schema / required
      Removed value: -[
-  "effectiveQuery",
-  "totalCount"
-]
  6. Changed16 schema fields changed
    • addedInput schema / properties / articleIndex
      Added value: +{
+  "default": 0,
+  "description": "Which article 'content' reads, 0-based against the issue's whole article sequence — the same absolute position 'articles' pages through with offset. Ignored by other operations.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / characterLimit
      Added value: +{
+  "default": 25000,
+  "description": "Maximum characters to return for 'content' (1-100000). Legislative documents run past a million characters, so a full bill takes several windows.",
+  "maximum": 100000,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / characterOffset
      Added value: +{
+  "default": 0,
+  "description": "First character to return for 'content', 0-based. Offsets are exact and are never snapped to a section or paragraph break, so feeding the response's nextOffset back walks the whole document with every character returned exactly once.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / format
      Added value: +{
+  "default": "text",
+  "description": "Document format for 'content'. 'text' is GPO's Formatted Text — plain, pre-formatted print output, published for every document checked. 'xml' prefers United States Legislative Markup and falls back to Formatted XML; it exists on some bill text versions and on no committee report or Congressional Record article. PDF is not retrieved — read one at the format URLs 'text'/'articles' return.",
+  "enum": [
+    "text",
+    "xml"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / issueNumber / anyOf
      Added value: +[
+  {
+    "description": "Positive integer form.",
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "description": "Digit-string form, as list rows carry it.",
+    "pattern": "^0*[1-9]\\d*$",
+    "type": "string"
+  }
+]
    • changedInput schema / properties / issueNumber / description
      Previous value: -"Issue number within a volume. Required for 'articles'."New value: +"Issue number within a volume. Required for 'articles' and 'content'. List rows carry this as a string (e.g. \"109\") — both forms are accepted."
    • removedInput schema / properties / issueNumber / exclusiveMinimum
      Removed value: -0
    • removedInput schema / properties / issueNumber / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / issueNumber / type
      Removed value: -"integer"
    • changedInput schema / properties / operation / enum
      Previous value: -[
-  "list",
-  "issues",
-  "articles"
-]New value: +[
+  "list",
+  "issues",
+  "articles",
+  "content"
+]
    • addedInput schema / properties / volumeNumber / anyOf
      Added value: +[
+  {
+    "description": "Positive integer form.",
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "description": "Digit-string form, as list rows carry it.",
+    "pattern": "^0*[1-9]\\d*$",
+    "type": "string"
+  }
+]
    • changedInput schema / properties / volumeNumber / description
      Previous value: -"Volume number. Required for 'issues' and 'articles'."New value: +"Volume number. Required for 'issues', 'articles', and 'content'. Accepts a number or the digit-string form list rows carry."
    • removedInput schema / properties / volumeNumber / exclusiveMinimum
      Removed value: -0
    • removedInput schema / properties / volumeNumber / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / volumeNumber / type
      Removed value: -"integer"
    • changedOutput schema / required
      Previous value: -[
-  "data",
-  "pagination",
-  "effectiveQuery",
-  "totalCount"
-]New value: +[
+  "effectiveQuery",
+  "totalCount"
+]
  7. Changed5 schema fields changed
    • addedOutput schema / properties / effectiveQuery
      Added value: +{
+  "description": "The browse scope and applied filters.",
+  "type": "string"
+}
    • addedOutput schema / properties / notice
      Added value: +{
+  "description": "Guidance when results are empty, a page is past the end, or a caveat applies.",
+  "type": "string"
+}
    • removedOutput schema / properties / query
      Removed value: -{
-  "description": "Echo of the applied filters for this query. Rendered as the first line of the response so the caller can confirm what was searched.",
-  "type": "string"
-}
    • addedOutput schema / properties / totalCount
      Added value: +{
+  "description": "Total results across all pages.",
+  "type": "number"
+}
    • changedOutput schema / required
      Previous value: -[
-  "data",
-  "pagination"
-]New value: +[
+  "data",
+  "pagination",
+  "effectiveQuery",
+  "totalCount"
+]
  8. Changed5 schema fields changed
    • removedOutput schema / description
      Removed value: -"Congressional Record data from Congress.gov API."
    • addedOutput schema / properties / data
      Added value: +{
+  "description": "Result rows. Per-tool item shape is rendered in the markdown body.",
+  "items": {
+    "additionalProperties": {},
+    "description": "Upstream JSON record. Per-tool item shape is rendered in the markdown body.",
+    "properties": {},
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / pagination
      Added value: +{
+  "additionalProperties": false,
+  "description": "Pagination metadata: total count and next offset.",
+  "properties": {
+    "count": {
+      "description": "Total result count across all pages.",
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "nextOffset": {
+      "anyOf": [
+        {
+          "maximum": 9007199254740991,
+          "minimum": 0,
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Offset to pass for the next page, or null when there are no more pages."
+    }
+  },
+  "required": [
+    "count"
+  ],
+  "type": "object"
+}
    • addedOutput schema / properties / query
      Added value: +{
+  "description": "Echo of the applied filters for this query. Rendered as the first line of the response so the caller can confirm what was searched.",
+  "type": "string"
+}
    • addedOutput schema / required
      Added value: +[
+  "data",
+  "pagination"
+]
  9. First observed

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world behavior, so the safety profile is covered. The description adds genuinely useful operational context beyond that: 'content' returns a bounded character window at a time, and 'articles' returns format URLs while PDF is not retrieved — helpful for an agent planning reads.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the resource definition, then the hierarchy and per-operation guidance in three tight sentences. There is mild repetition of the list/issues/articles sequence, but each sentence carries navigational value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and rich annotations, the description needn't explain return shapes, and it covers the hierarchical navigation model well. Minor gaps: it doesn't mention pagination behavior or that volume/issue numbers are required for downstream operations, though the schema covers those.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all nine parameters are documented in the schema, including the characterOffset/characterLimit windowing semantics. The description reinforces the operation roles but adds no syntax or format detail beyond what the schema already provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Browse the daily Congressional Record — floor speeches, debates, and legislative text' — which is clearly distinct from the bill/committee/member-focused siblings. It does not explicitly name or contrast a sibling, which keeps it just under a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit navigation flow: 'list' for volumes, 'issues' for what's in a volume, 'articles' for individual speeches, and 'content' to read article text. This tells the agent when each operation applies and how they chain, though it doesn't state exclusions or when to prefer a sibling tool (e.g., full bill text via bill_lookup).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All congressgov-mcp-server toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources